{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09237875288683603,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009237875288683603,
      "grad_norm": 3.087350606918335,
      "learning_rate": 2e-05,
      "loss": 4.4439,
      "step": 1
    },
    {
      "epoch": 0.009237875288683603,
      "eval_loss": 4.263659954071045,
      "eval_runtime": 1.2874,
      "eval_samples_per_second": 35.731,
      "eval_steps_per_second": 17.865,
      "step": 1
    },
    {
      "epoch": 0.018475750577367205,
      "grad_norm": 3.7086079120635986,
      "learning_rate": 4e-05,
      "loss": 4.2244,
      "step": 2
    },
    {
      "epoch": 0.02771362586605081,
      "grad_norm": 2.991490364074707,
      "learning_rate": 6e-05,
      "loss": 3.8896,
      "step": 3
    },
    {
      "epoch": 0.02771362586605081,
      "eval_loss": 4.238379955291748,
      "eval_runtime": 1.2912,
      "eval_samples_per_second": 35.627,
      "eval_steps_per_second": 17.813,
      "step": 3
    },
    {
      "epoch": 0.03695150115473441,
      "grad_norm": 2.6365671157836914,
      "learning_rate": 8e-05,
      "loss": 2.9142,
      "step": 4
    },
    {
      "epoch": 0.046189376443418015,
      "grad_norm": 2.907968759536743,
      "learning_rate": 0.0001,
      "loss": 3.6055,
      "step": 5
    },
    {
      "epoch": 0.05542725173210162,
      "grad_norm": 3.0383033752441406,
      "learning_rate": 0.00012,
      "loss": 3.7958,
      "step": 6
    },
    {
      "epoch": 0.05542725173210162,
      "eval_loss": 3.9253804683685303,
      "eval_runtime": 1.3655,
      "eval_samples_per_second": 33.687,
      "eval_steps_per_second": 16.844,
      "step": 6
    },
    {
      "epoch": 0.06466512702078522,
      "grad_norm": 2.7021243572235107,
      "learning_rate": 0.00014,
      "loss": 3.0099,
      "step": 7
    },
    {
      "epoch": 0.07390300230946882,
      "grad_norm": 2.807525634765625,
      "learning_rate": 0.00016,
      "loss": 3.4039,
      "step": 8
    },
    {
      "epoch": 0.08314087759815242,
      "grad_norm": 2.5225908756256104,
      "learning_rate": 0.00018,
      "loss": 3.1089,
      "step": 9
    },
    {
      "epoch": 0.08314087759815242,
      "eval_loss": 3.4916129112243652,
      "eval_runtime": 1.3584,
      "eval_samples_per_second": 33.863,
      "eval_steps_per_second": 16.931,
      "step": 9
    },
    {
      "epoch": 0.09237875288683603,
      "grad_norm": 2.459866523742676,
      "learning_rate": 0.0002,
      "loss": 2.4674,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 512599763976192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}